Grok 4.6

by xai · family grok

Facts

Release date	2026-08-12
Retired date	—
Knowledge cutoff	2026-02-01
Context (max)	500,000
Max output	—
Modalities	text, image → text
Aliases	`grok-4.6`
Open weights	no
Description	Reasoning model; adds xhigh over 4.5; returns summarized reasoning via streamed reasoning_content deltas.

Unknown values are shown as —.

Intelligence Index v4.1.1: 61 · high effort · Source: Artificial Analysis (accessed 2026-08-20)

Offerings

Provider	Wire ID	Endpoint	Protocol	Status	Price (USD / Mtok)	Reasoning
OpenCode Go	`grok-4.6`	go-responses	openai-responses	ga	—	effort · default on · mandatory · returns reasoning_content · round-trips encrypted_content
OpenCode Zen	`grok-4.6`	responses	openai-responses	ga	2.00 / 6.00	effort · default on · mandatory · returns reasoning_content · round-trips encrypted_content
OpenRouter	`x-ai/grok-4.6`	chat-completions	openai-chat	ga	2.00 / 6.00	effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content
xAI	`grok-4.6`	v1-chat-completions	openai-chat	ga	2.00 / 6.00	effort · default on · mandatory · returns reasoning_content
xAI	`grok-4.6`	v1-responses	openai-responses	ga	2.00 / 6.00	effort · default on · mandatory · returns reasoning_content · round-trips encrypted_content

Reasoning controls

OpenCode Go· grok-4.6· go-responses effort

reasoning.effort lowmediumhigh●xhigh

effort · default on · mandatory · returns reasoning_content · round-trips encrypted_content

OpenCode Zen· grok-4.6· responses effort

reasoning.effort lowmediumhigh●xhigh

effort · default on · mandatory · returns reasoning_content · round-trips encrypted_content

OpenRouter· x-ai/grok-4.6· chat-completions effort

reasoning.effort lowmediumhigh●xhighmax

effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content

xAI· grok-4.6· v1-chat-completions effort

reasoning_effort lowmediumhigh●xhigh

effort · default on · mandatory · returns reasoning_content

xAI· grok-4.6· v1-responses effort

reasoning.effort lowmediumhigh●xhigh

effort · default on · mandatory · returns reasoning_content · round-trips encrypted_content

Example requests

OpenCode Go · openai-responses · grok-4.6

curl 'https://opencode.ai/zen/go/v1/responses' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "grok-4.6",
  "input": "Tell me about the weather.",
  "reasoning": {
    "effort": "high"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://opencode.ai/zen/go/v1/responses",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "grok-4.6",
      "input": "Tell me about the weather.",
      "reasoning": {
        "effort": "high"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://opencode.ai/zen/go/v1/responses", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "grok-4.6",
    "input": "Tell me about the weather.",
    "reasoning": {
      "effort": "high"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include encrypted_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

OpenCode Zen · openai-responses · grok-4.6

curl 'https://opencode.ai/zen/v1/responses' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "grok-4.6",
  "input": "Tell me about the weather.",
  "reasoning": {
    "effort": "high"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://opencode.ai/zen/v1/responses",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "grok-4.6",
      "input": "Tell me about the weather.",
      "reasoning": {
        "effort": "high"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://opencode.ai/zen/v1/responses", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "grok-4.6",
    "input": "Tell me about the weather.",
    "reasoning": {
      "effort": "high"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include encrypted_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

OpenRouter · openai-chat · x-ai/grok-4.6

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "x-ai/grok-4.6",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "high"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "x-ai/grok-4.6",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "high"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "x-ai/grok-4.6",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "high"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

xAI · openai-chat · grok-4.6

curl 'https://api.x.ai/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "grok-4.6",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "high"
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.x.ai/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "grok-4.6",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "high"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.x.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "grok-4.6",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "high"
  }),
})
console.log(await resp.json())

xAI · openai-responses · grok-4.6

curl 'https://api.x.ai/v1/responses' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "grok-4.6",
  "input": "Tell me about the weather.",
  "reasoning": {
    "effort": "high"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.x.ai/v1/responses",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "grok-4.6",
      "input": "Tell me about the weather.",
      "reasoning": {
        "effort": "high"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.x.ai/v1/responses", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "grok-4.6",
    "input": "Tell me about the weather.",
    "reasoning": {
      "effort": "high"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include encrypted_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).